EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

server : added --no-prefill-assistant flag (#13608)

Browse Source 
* added no-prefill-assistant flag

* reworded documentation comment

* updated server README.md
This commit is contained in:
Isaac McFadyen
2025-05-17 17:59:48 -04:00
committed by GitHub
parent e3a7cf6c5b
commit 6a2bc8bfb7
5 changed files with 17 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.h
View File

@@ -368,6 +368,7 @@ struct common_params {
bool use_jinja = false; // NOLINT
bool enable_chat_template = true;
common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK;
bool prefill_assistant = true; // if true, any trailing assistant message will be prefilled into the response
std::vector<std::string> api_keys;